At z greater than or similar to 1, the distinction between merging and “normal” star-forming galaxies based on single band morphology is often hampered by the presence of large clumps which result in a disturbed, merger-like appearance even in rotationally supported disks. In this paper we discuss how a classification based on canonical, non-parametric structural indices measured on resolved stellar mass maps, rather than on single-band images, reduces the misclassification of clumpy but not merging galaxies. We calibrate the mass-based selection of mergers using the MIRAGE hydrodynamical numerical simulations of isolated and merging galaxies which span a stellar mass range of 10(9.8)-10(10.6) M-circle dot and merger ratios between 1:1-1:6.3. These simulations are processed to reproduce the typical depth and spatial resolution of observed Hubble Ultra Deep Field (HUDF) data. We test our approach on a sample of real z similar or equal to 2 galaxies with kinematic classification into disks or mergers and on similar to 100 galaxies in the HUDF field with photometric/spectroscopic redshift between 1.5 \textless= z \textless= 3 and M \textgreater 10(9.4) M-circle dot. We find that a combination of the asymmetry A(MASS) and M-20, (MASS) indices measured on the stellar mass maps can efficiently identify real (major) mergers with less than or similar to 20% contamination from clumpy disks in the merger sample. This mass-based classification cannot be reproduced in star-forming galaxies by H-band measurements alone, which instead result in a contamination from clumpy galaxies which can be as high as 50%. Moreover, we find that the mass-based classification always results in a lower contamination from clumpy galaxies than an H-band classification, regardless of the depth of the imaging used (e.g., CANDELS versus HUDF).